《MongoDB高手课》学习记录（第十二天）

写在前面

今天是第一章复习的最后一个部分，聚合的内容。课程中关于聚合的内容讲的不多，今天主要参考一些官方文档的例子。

第十二天

复习一下关于聚合的知识

1. 聚合就是处理类似group by,as，left join等的操作，通过对集合中数据的梳理来输出需要的数据
2. 聚合可以作用在多个集合上
3. 聚合运算的过程叫做Pipeline，Pipeline是由多个Stage构成的数组，每个Stage都是在上一个Stage的基础上进行运算，最终输出需要的结果

与 MySQL 操作的比较

SQL	MongoDB
WHERE	$match
GROUP BY	$group
HAVING	$match
SELECT	$project
ORDER BY	$sort
LIMIT	$limit
SUM()	$sum
COUNT()	$sum / $sortByCount
join	$lookup
SELECT INTO NEW_TABLE	$out
MERGE INTO TABLE	$merge (Available starting in MongoDB 4.2)

练习

> db.orders.insertOne({
   cust_id: "abc123",
    ord_date: ISODate("2012-11-02T17:04:11.102Z"),
    status: 'A',
   price: 50,
    items: [ { sku: "xxx", qty: 25, price: 1 },
             { sku: "yyy", qty: 25, price: 1 } ]
  })
{
        "acknowledged" : true,
        "insertedId" : ObjectId("5e09c94ca033b8cfbf60470c")
}
>

SELECT COUNT(*) AS count
FROM orders

db.orders.aggregate( [
   {
     $group: {
        _id: null,
        count: { $sum: 1 }
     }
   }
] )

SELECT SUM(price) AS total
FROM orders

db.orders.aggregate( [
   {
     $group: {
        _id: null,
        total: { $sum: "$price" }
     }
   }
] )

SELECT cust_id,
       SUM(price) AS total
FROM orders
GROUP BY cust_id

db.orders.aggregate( [
   {
     $group: {
        _id: "$cust_id",
        total: { $sum: "$price" }
     }
   }
] )

SELECT cust_id,
       SUM(price) AS total
FROM orders
GROUP BY cust_id
ORDER BY total

db.orders.aggregate( [
   {
     $group: {
        _id: "$cust_id",
        total: { $sum: "$price" }
     }
   },
   { $sort: { total: 1 } }
] )

SELECT cust_id,
       ord_date,
       SUM(price) AS total
FROM orders
GROUP BY cust_id,
         ord_date

db.orders.aggregate( [
   {
     $group: {
        _id: {
           cust_id: "$cust_id",
           ord_date: { $dateToString: {
              format: "%Y-%m-%d",
              date: "$ord_date"
           }}
        },
        total: { $sum: "$price" }
     }
   }
] )

SELECT cust_id,
       count(*)
FROM orders
GROUP BY cust_id
HAVING count(*) > 1

db.orders.aggregate( [
   {
     $group: {
        _id: "$cust_id",
        count: { $sum: 1 }
     }
   },
   { $match: { count: { $gt: 1 } } }
] )

SELECT cust_id,
       ord_date,
       SUM(price) AS total
FROM orders
GROUP BY cust_id,
         ord_date
HAVING total > 250

db.orders.aggregate( [
   {
     $group: {
        _id: {
           cust_id: "$cust_id",
           ord_date: { $dateToString: {
              format: "%Y-%m-%d",
              date: "$ord_date"
           }}
        },
        total: { $sum: "$price" }
     }
   },
   { $match: { total: { $gt: 250 } } }
] )

SELECT cust_id,
       SUM(price) as total
FROM orders
WHERE status = 'A'
GROUP BY cust_id

db.orders.aggregate( [
   { $match: { status: 'A' } },
   {
     $group: {
        _id: "$cust_id",
        total: { $sum: "$price" }
     }
   }
] )

SELECT cust_id,
       SUM(price) as total
FROM orders
WHERE status = 'A'
GROUP BY cust_id
HAVING total > 250

db.orders.aggregate( [
   { $match: { status: 'A' } },
   {
     $group: {
        _id: "$cust_id",
        total: { $sum: "$price" }
     }
   },
   { $match: { total: { $gt: 250 } } }
] )

SELECT cust_id,
       SUM(li.qty) as qty
FROM orders o,
     order_lineitem li
WHERE li.order_id = o.id
GROUP BY cust_id

db.orders.aggregate( [
   { $unwind: "$items" },
   {
     $group: {
        _id: "$cust_id",
        qty: { $sum: "$items.qty" }
     }
   }
] )

SELECT COUNT(*)
FROM (SELECT cust_id,
             ord_date
      FROM orders
      GROUP BY cust_id,
               ord_date)
      as DerivedTable

db.orders.aggregate( [
   {
     $group: {
        _id: {
           cust_id: "$cust_id",
           ord_date: { $dateToString: {
              format: "%Y-%m-%d",
              date: "$ord_date"
           }}
        }
     }
   },
   {
     $group: {
        _id: null,
        count: { $sum: 1 }
     }
   }
] )

最后

第一章到此结束，明天开始第二章的学习